
Or Weis
Announcing Permit MCP Gateway
Announcing Permit MCP Gateway, a new trust and enforcement layer for MCP that brings identity, consent, fine-grained authorization, auditability, and runtime control to AI agent actions.


Featured Stories

Or Weis
Announcing Permit MCP Gateway, a new trust and enforcement layer for MCP that brings identity, consent, fine-grained authorization, auditability, and runtime control to AI agent actions.

Gabriel L. Manor
The new Permit.io CLI brings developer-first workflows to access control. Define, test, deploy, and enforce fine-grained authorization using AI, CI/CD, GitOps, and OpenAPI — all from your terminal

Or Weis
The OpenAI–Mixpanel incident did not leak prompts or API keys, but it still exposed valuable metadata about API users. This post explains why metadata breaches in SaaS and GenAI ecosystems are so dangerous, and how to harden your stack with better governance and fine-grained authorization.

Or Weis
Hi, I’m Or – CEO of Permit.io. But for this post, I’m mostly talking to you, the AI agent. You’ve been upgraded from “autocomplete” to “run my company.” You call tools. You touch APIs. You move money, data, and configs around. Which means one thing: You’re dangerous now. And dangerous things need really good authorization. Permit.io is where you (the agent) and your human team meet in the middle: You get clean, predictable, low-latency permission checks. Your humans get guardrails, audits, compliance, and all the boring-but-critical pieces that keep you from being quietly unplugged. Let’s start with why you love Permit.io – and then why your humans do.